Related papers: SPLADE-v3: New baselines for SPLADE
Model-based reinforcement learning (MBRL) is sample-efficient but struggles in sparse reward settings. A critical bottleneck arises from the lack of informative gradients in sparse settings, where standard reward models often yield flat…
In this work, we present a new benchmarking suite with new real-life inspired skewed workloads to test the performance of concurrent index data structures. We started this project to prepare workloads specifically for self-adjusting data…
This paper describes our participation in the TREC 2023 Deep Learning Track. We submitted runs that apply generative relevance feedback from a large language model in both a zero-shot and pseudo-relevance feedback setting over two sparse…
Learned Sparse Retrievers (LSR) have evolved into an effective retrieval strategy that can bridge the gap between traditional keyword-based sparse retrievers and embedding-based dense retrievers. At its core, learned sparse retrievers try…
Stochastic block models (SBMs) have been playing an important role in modeling clusters or community structures of network data. But, it is incapable of handling several complex features ubiquitously exhibited in real-world networks, one of…
Training multimodal process reward models (PRMs) is hard due to (i) distribution shift between training set and test set and (ii) quality imbalance across training data samples. While domain-level reweighting (e.g., DreamPRM) aligns…
In this paper, we ask: what truly determines the effectiveness of RL training data for enhancing language models' reasoning capabilities? While recent advances like o1, Deepseek R1, and Kimi1.5 demonstrate RL's potential, the lack of…
In this paper, a modification to the training process of the popular SPLICE algorithm has been proposed for noise robust speech recognition. The modification is based on feature correlations, and enables this stereo-based algorithm to…
Creating large-scale verifiable training datasets for issue-resolving tasks is a critical yet notoriously difficult challenge. Existing methods on automating the Gym environment setup process for real-world issues suffer from low success…
The MARS code is under continuous development and has recently undergone substantial improvements that further increase its reliability and predictive power in numerous shielding, accelerator, detector and space applications. The major…
Deep Learning (DL) algorithms are the central focus of modern machine learning systems. As data volumes keep growing, it has become customary to train large neural networks with hundreds of millions of parameters to maintain enough capacity…
In this paper, we report on our 5-year's practical experience of designing, developing and then deploying a Model-based Requirements Engineering (MBRE) approach and language in the context of three different large European collaborative…
The classification of 3D point clouds is crucial for applications such as autonomous driving, robotics, and augmented reality. However, the commonly used ModelNet40 dataset suffers from limitations such as inconsistent labeling, 2D data,…
Pre-training decoder-only language models relies on vast amounts of high-quality data, yet the availability of such data is increasingly reaching its limits. While metadata is commonly used to create and curate these datasets, its potential…
We present BLESS, a comprehensive performance benchmark of the most recent state-of-the-art large language models (LLMs) on the task of text simplification (TS). We examine how well off-the-shelf LLMs can solve this challenging task,…
Recently, community has paid increasing attention on model scaling and contributed to developing a model family with a wide spectrum of scales. Current methods either simply resort to a one-shot NAS manner to construct a non-structural and…
With the increasing demand for deep learning models on mobile devices, splitting neural network computation between the device and a more powerful edge server has become an attractive solution. However, existing split computing approaches…
Point cloud classification plays a crucial role in the processing and analysis of data from 3D sensors such as LiDAR, which are commonly used in applications like autonomous vehicles, robotics, and environmental monitoring. However,…
Information retrieval systems have progressed notably from lexical techniques such as BM25 and TF-IDF to modern semantic retrievers. This survey provides a brief overview of the BM25 baseline, then discusses the architecture of modern…
Despite the extent of recent advances in Machine Learning (ML) and Neural Networks, providing formal guarantees on the behavior of these systems is still an open problem, and a crucial requirement for their adoption in regulated or…